Ratel: Dynamic Tool Control for Agents
jack1689 · hn · 2026-07-17
Ratel is a library for agents designed to let them retain a complete inventory of tools and skills while dynamically exposing only the few tools actually needed in any given turn. This helps reduce context bloat, hallucinations, and high token costs.
The author notes it is already being used in production: after dynamically loading 300+ tools into the context, one team used Ratel to cut token costs by up to 81% in the first month without sacrificing accuracy. It supports keyword and semantic retrieval, runs purely in-process without extra infrastructure, is framework-agnostic, offers TypeScript and Python versions, and exposes OpenTelemetry metrics.
More from coding & agent
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- A better path to agent autonomy is running waves, finding friction, and iterating — JnBrymn · 2026-07-22
- Coding agents are heading toward an AI-writes, AI-reviews, human-approves workflow — aftahi_ai · 2026-07-22
- oMLX 0.5.2 adds Mac menu-bar stats, low-bit decode kernels, and faster downloads — awnihannun · 2026-07-22
- GitHub review bot hits its PR limit and forces a 39-minute cooldown — DanielLockyer · 2026-07-22
- Max reasoning effort appears to be mobile-only in Codex Remote, not desktop — GabGarrett · 2026-07-22